Triangle Generative Adversarial Networks

By Zhe Gan, Liqun Chen, Weiyao Wang, Yunchen Pu, Yizhe Zhang, Hao Liu, Chunyuan Li, Lawrence Carin. 2017

142 citations recorded by the source corpus.

A Triangle Generative Adversarial Network ($\Delta$-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. $\Delta$-GAN consists of four neural networks, two generators and two discriminators. The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs. The generators and discriminators are trained together using adversarial learning. Under mild assumptions, in theory the joint distributions characterized by the two generators concentrate to the data distribution. In experiments, three different kinds of domain pairs are considered, image-label, image-image and image-attribute pairs. Experiments on semi-supervised image classification, image-to-image translation and attribute-based image generation demonstrate the superiority of the proposed approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization (2018, methodology): “To address this issue, inspired by recent work on leveraging “cycle consistency” for image generation [13, 25], we implement a dual objective that treats source and target equally, by complementing the objective in Eqn.”
ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching (2017, background): “When tying the weights of discriminators of two conditional GANs, ALICE recovers Triangle GAN [16].”
High-Fidelity Image Generation With Fewer Labels (2019, methodology): “, 2017) or harness joint distribution (of labels and data) matching for semi-supervised learning (Gan et al., 2017).”
Deconvolutional Paragraph Representation Learning (2017, background): “This deconvolutional module can also be leveraged as building block in VAE[30, 31] or GAN[32, 33]”
Small Sample Learning in Big Data Era (2018, background): “The early work along this line focused on semi-supervised learning with generative model, aroused the attention of many works (Chen et al., 2016; Li et al., 2017a; Gan et al., 2017; Deng et al., 2017b).”
Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data (2018, methodology): “We follow the same evaluation methodology adopted in (Metz et al., 2016; Xiang & Li, 2017), which opt for an (Gan et al., 2017).”
A Survey of Unsupervised Deep Domain Adaptation (2018, methodology): “These networks can be trained with varying levels of supervision: the dataset may contain corresponding images in the domains (supervised [109, 265]), only a few corresponding images (semi-supervised [71]), or no corresponding images (unsupervised [118, 264, 290]). A popular and general-purpose supe”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “GANs’ Representative variants InfoGAN [14], cGANs [15], CycleGAN [16], f -GAN [17], WGAN [18], WGAN-GP [19], LS-GAN [20] Objective function LSGANs [21], [22], hinge loss based GAN [23]–[25], MDGAN [26], unrolled GAN [27], SN-GANs [23], RGANs [28] Skills ImprovedGANs [29], AC-GAN [30] LAPGAN [31], DC”
KDGAN: Knowledge Distillation with Generative Adversarial Networks (2018, background): “GAN has only recently been introduced to generate discrete data [16, 54, 55] because discrete data makes it difficult to pass gradients from a discriminator backward to update a generator.”
Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators (2018, background): “While some work has also focused on augmenting the number of generators [13, 14, 19], or even increasing both the number of generators and discriminators [7, 12, 16, 31], we will now turn our focus on methods that solely increases the number of discriminators in order to prevent mode collapse.”
Learning Neural Random Fields with Inclusive Auxiliary Generators (2018, unknown): “09 Triangle-GAN [46] 16.”
Triple Generative Adversarial Networks (2019, methodology): “Triangle-GAN [39] extends our conference version [61] by minimizing the Jensen Shannon divergence between every two joint distributions and demonstrating the effectiveness in applications such as the image to image translation.”
Evolutionary Generative Adversarial Networks (2018, methodology): “GANs have recently been successfully applied to image generation [4, 22, 9, 37], image editing [13, 31, 40, 32], video prediction[29, 8, 30], and many other tasks [38, 28, 17].”
A Survey on Deep Semi-Supervised Learning (2021, methodology): “CatGAN [32] 1:39ð 0:28Þ 19:58ð 0:58Þ ImprovedGAN [33] 0:93ð 0:07Þ 18:44ð 4:8Þ 8:11ð 1:3Þ 21:83ð 2:01Þ 18:63ð 2:32Þ GoodBadGAN [34] 0:80ð 0:1Þ 4:25ð 0:03Þ 14:41ð 0:30Þ Localized GAN [35] 5:48ð 0:29Þ 4:73ð 0:16Þ 17:44ð 0:25Þ 14:23ð 0:27Þ CT-GAN [36] 0:89ð 0:13Þ 9:98ð 0:21Þ ALI [37] 7:42ð 0:65Þ 19:98ð ”
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets (2018, methodology): “The caption features are obtained from a pretrained word-level CNN-LSTM autoencoder (Gan et al., 2017b), which aims to achieve a one-to-one mapping between the captions and the features.”
Symmetric Variational Autoencoder and Connections to Adversarial Learning (2017, methodology): “Consequently, [Pu et al., 2017] did not use adversarial learning to approximate the log-LRT, and therefore it cannot make the explicit connection to ALI and WGAN that were made in Sections 4.1 and 4.3, respectively.”